INDEX

Explanations

proper nouns, especially those related to politics, organizations, or locations.

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 beginnetje

-0.71

 estekak

-0.66

DispatchToProps

-0.63

헌

-0.58

Tentang

-0.57

 jöv

-0.57

曖昧さ回避

-0.56

 initComponents

-0.55

MathML

-0.54

🏻‍♀️

-0.54

POSITIVE LOGITS

+#+

0.60

 Zweiten

0.54

twimg

0.51

 propOrder

0.51

nischer

0.47

creativecommons

0.45

Награ

0.44

OrBuilder

0.44

enciado

0.44

MethodType

0.43

Activations Density 0.899%

proper nouns, especially those related to politics, organizations, or locations.

No Comments

No Known Activations